Transfer Learning (C3W2L07) November 18, 2019 9 By Stanley Isaacs CategoryArticles Blog 9 Comments Julian Harris says: February 11, 2018 at 11:25 am Once again thank you Andrew — you have a special way of communicating very complex concepts in a very understandable way. Question: what’s not touched on in the video is that as far as I’m aware it’s not immediately obvious what those lower level features from A actually are in a trained network. I know there’s been work to visualise what they are for images (and hence the realisation about edges, curves, dots etc because the visualisations showed this), but in general, I wasn’t aware of a way of visualising low-level layers in a way that helps you choose which task A could benefit task B. This to me implies there might be value in transfer learning across tasks that don’t necessarily have obviously similar low-level features. Is that reasonable? Reply Raul Maldonado says: March 31, 2018 at 8:18 pm is this video part of a bigger course? Reply md asadullah turja says: June 14, 2018 at 7:52 pm Great explanation !! Reply Nands says: October 27, 2018 at 5:34 pm amazing! Reply Buckler Co says: November 27, 2018 at 2:30 pm Video is done at 1:25 Lol!! he explained it so simply. Reply Roger AB says: March 12, 2019 at 7:46 pm Transfer learning is the key to AGI, once a Neural Network learns the patterns of logical relationships and it is able to transfer that learning and apply it to new problems an AI will be able to draw intelligent conclusions. All that is needed is an AI that picks patterns in logical problems and learns from it's conclusions, once it has learned it needs to pick similarities between new problems and the old already solved ones to transfer it's neural pathways but also COMBINE them to deduct new conclusions( combine them taking into consideration the problem that is being aimed to solve ), conclusions which will be useful to solve new problems and so on… ( The key concept here is to find a way to 'COMBINE' trained neural nets to build newer, smarter and more general ones, an AI should be trained to learn to combine specific neural nets to solve new problems related to the ones already solved, then use that AI that combines pathways to assist in the combination of neural nets for different problems, combining not only neural nets themselves but the neural nets that were used to combine nets in the past to create better more general combinations of nets ). All this will keep building on itself and AGI will become more capable faster and faster as time passes by. Reply MOHSIN ALI says: March 13, 2019 at 2:21 pm thank you sir Reply Shashank Sharma says: May 13, 2019 at 7:00 am How to handle input data if the aspect ratio of pre-trained models are different than input images?? for example, Say aspect ratio for Task A image recognition is 224 x 224 and aspect ratio for Task B diagnosis is 250 x 125 Reply Gautam Kishore Shahi says: August 4, 2019 at 8:12 pm can we use the concept of transfer learning on SVM? Reply Leave a Reply Cancel reply Your email address will not be published. Required fields are marked *Comment Name * Email * Save my name, email, and website in this browser for the next time I comment.